Extreme precipitation is a considerable contributor to meteorological disasters and there is a great need to mitigate its socioeconomic effects through skilful nowcasting that has high resolution, long lead times and local details. Current methods are subject to blur, dissipation, intensity or location errors, with physics-based numerical methods struggling to capture pivotal chaotic dynamics such as convective initiation and data-driven learning methods failing to obey intrinsic physical laws such as advective conservation. We present NowcastNet, a nonlinear nowcasting model for extreme precipitation that unifies physical-evolution schemes and conditional-learning methods into a neural-network framework with end-to-end forecast error optimization. On the basis of radar observations from the USA and China, our model produces physically plausible precipitation nowcasts with sharp multiscale patterns over regions of 2,048 km × 2,048 km and with lead times of up to 3 h. In a systematic evaluation by 62 professional meteorologists from across China, our model ranks first in 71% of cases against the leading methods. NowcastNet provides skilful forecasts at light-to-heavy rain rates, particularly for extreme-precipitation events accompanied by advective or convective processes that were previously considered intractable.
References
Wang, Y. et al. Guidelines for Nowcasting Techniques (World Meteorological Organization, 2017).
Pendergrass, A. G. What precipitation is extreme? Science 360, 1072–1073 (2018).
[DOI: 10.1126/science.aat1871]
Smith, A. WMO Atlas of Mortality and Economic Losses from Weather, Climate and Water Extremes (1970–2019) (World Meteorological Organization, 2021).
Ravuri, S. et al. Skilful precipitation nowcasting using deep generative models of radar. Nature 597, 672–677 (2021).
[DOI: 10.1038/s41586-021-03854-z]
Karniadakis, G. E. et al. Physics-informed machine learning. Nat. Rev. Phys. 3, 422–440 (2021).
[DOI: 10.1038/s42254-021-00314-5]
Berne, A., Delrieu, G., Creutin, J.-D. & Obled, C. Temporal and spatial resolution of rainfall measurements required for urban hydrology. J. Hydrol. 299, 166–179 (2004).
[DOI: 10.1016/S0022-1694(04)00363-4]
Sun, J. et al. Use of NWP for nowcasting convective precipitation: recent progress and challenges. Bull. Am. Meteorol. Soc. 95, 409–426 (2014).
[DOI: 10.1175/BAMS-D-11-00263.1]
Pierce, C., Seed, A., Ballard, S., Simonin, D. & Li, Z. in Doppler Radar Observations (eds Bech, J. & Chau, J. L.) Ch. 4 (IntechOpen, 2012).
Pulkkinen, S. et al. Pysteps: an open-source Python library for probabilistic precipitation nowcasting (v1.0). Geosci. Model Dev. 12, 4185–4219 (2019).
[DOI: 10.5194/gmd-12-4185-2019]
Ruzanski, E., Chandrasekar, V. & Wang, Y. The CASA nowcasting system. J. Atmos. Ocean. Technol. 28, 640–655 (2011).
[DOI: 10.1175/2011JTECHA1496.1]
Roca-Sancho, J., Berenguer, M., Zawadzki, I. & Sempere-Torres, D. in Proc. Conference on Radar Meteorology P7.2 (2009).
Shi, X. et al. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Advances in Neural Information Processing Systems Vol. 28 (eds Cortes, C. et al.) (NIPS, 2015).
Wang, Y. et al. PredRNN: a recurrent neural network for spatiotemporal predictive learning. IEEE Trans. Pattern Anal. Mach. Intell. 45, 2208–2225 (2022).
[DOI: 10.1109/TPAMI.2022.3165153]
Ayzel, G., Scheffer, T. & Heistermann, M. RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting. Geosci. Model Dev. 13, 2631–2644 (2020).
[DOI: 10.5194/gmd-13-2631-2020]
Espeholt, L. et al. Deep learning for twelve hour precipitation forecasts. Nat. Commun. 13, 5145 (2022).
Franch, G. et al. Precipitation nowcasting with orographic enhanced stacked generalization: improving deep learning predictions on extreme events. Atmosphere 11, 267 (2020).
[DOI: 10.3390/atmos11030267]
Crane, R. K. Space-time structure of rain rate fields. J. Geophys. Res. Atmos. 95, 2011–2020 (1990).
[DOI: 10.1029/JD095iD03p02011]
Seed, A. A dynamic and spatial scaling approach to advection forecasting. J. Appl. Meteorol. 42, 381–388 (2003).
[DOI: 10.1175/1520-0450(2003)042<0381]
Weyn, J. A. & Durran, D. R. The scale dependence of initial-condition sensitivities in simulations of convective systems over the southeastern United States. Q. J. R. Meteorol. Soc. 145, 57–74 (2019).
[DOI: 10.1002/qj.3367]
Park, T., Liu, M.-Y., Wang, T.-C. & Zhu, J.-Y. in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2337–2346 (IEEE, 2019).
Goodfellow, I. et al. Generative adversarial nets. In Advances in Neural Information Processing Systems Vol. 27 (eds Ghahramani, Z. et al.) (NIPS, 2014).
Germann, U. & Zawadzki, I. Scale-dependence of the predictability of precipitation from continental radar images. Part I: description of the methodology. Mon. Weather Rev. 130, 2859–2873 (2002).
[DOI: 10.1175/1520-0493(2002)130<2859]
He, K., Zhang, X., Ren, S. & Sun, J. in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778 (IEEE, 2016).
Sobel, I. & Feldman, G. A 3x3 isotropic gradient operator for image processing. (1968).
Imhoff, R., Brauer, C., Overeem, A., Weerts, A. & Uijlenhoet, R. Spatial and temporal evaluation of radar rainfall nowcasting techniques on 1,533 events. Water Resour. Res. 56, e2019WR026723 (2020).
[DOI: 10.1029/2019WR026723]
Jiang, J., Shu, Y., Wang, J. & Long, M. Transferability in deep learning: a survey. Preprint at https://arxiv.org/abs/2201.05867 (2022).
Jolliffe, I. T. & Stephenson, D. B. Forecast Verification: A Practitioner’s Guide in Atmospheric Science (Wiley, 2012).
Sinclair, S. & Pegram, G. Empirical Mode Decomposition in 2-D space and time: a tool for space-time rainfall analysis and nowcasting. Hydrol. Earth Syst. Sci. 9, 127–137 (2005).
[DOI: 10.5194/hess-9-127-2005]
Ronneberger, O., Fischer, P. & Brox, T. in Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention 234–241 (MICCAI, 2015).
Xu, G. & Chandrasekar, V. Radar storm motion estimation and beyond: A spectral algorithm and radar observation based dynamic model. In Proc. International Symposium on Nowcasting and Very Short Range Forecasting (World Meteorological Organization, 2005).
Miyato, T., Kataoka, T., Koyama, M. & Yoshida, Y. Spectral normalization for generative adversarial networks. In Proc. International Conference on Learning Representations (ICLR, 2018).
Hofinger, M. et al. In Proc. European Conference on Computer Vision 770–786 (Springer, 2020).
Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. In Proc. International Conference on Learning Representations (ICLR, 2015).
Ulyanov, D., Vedaldi, A. & Lempitsky, V. Instance normalization: the missing ingredient for fast stylization. Preprint at https://arxiv.org/abs/1607.08022 (2016).
Kirkpatrick, J. et al. Overcoming catastrophic forgetting in neural networks. Proc. Natl Acad. Sci. 114, 3521–3526 (2017).
[DOI: 10.1073/pnas.1611835114]
Wang, Y., Long, M., Wang, J., Gao, Z. & Yu, P. S. In Advances in Neural Information Processing Systems Vol. 30 (eds Guyon, I. et al.) 879–888 (NIPS, 2017).
Zhang, J. et al. National Mosaic and Multi-sensor QPE (NMQ) system: description, results, and future plans. Bull. Am. Meteorol. Soc. 92, 1321–1338 (2011).
[DOI: 10.1175/2011BAMS-D-11-00047.1]
